Prediction of illness remission in patients with Obsessive-Compulsive Disorder with supervised machine learning.

INTRODUCTION: The course of OCD differs widely among OCD patients, varying from chronic symptoms to full remission. No tools for individual prediction of OCD remission are currently available. This study aimed to develop a machine learning algorithm to predict OCD remission after two years, using solely predictors easily accessible in the daily clinical routine. METHODS: Subjects were recruited in a longitudinal multi-center study (NOCDA). Gradient boosted decision trees were used as supervised machine learning technique. The training of the algorithm was performed with 227 predictors and 213 observations collected in a single clinical center. Hyper-parameter optimization was performed with cross-validation and a Bayesian optimization strategy. The predictive performance of the algorithm was subsequently tested in an independent sample of 215 observations collected in five different centers. Between-center differences were investigated with a bootstrap resampling approach. RESULTS: The average predictive performance of the algorithm in the test centers resulted in an AUROC of 0.7820, a sensitivity of 73.42%, and a specificity of 71.45%. Results also showed a significant between-center variation in the predictive performance. The most important predictors resulted related to OCD severity, OCD chronic course, use of psychotropic medications, and better global functioning. LIMITATIONS: All recruiting centers followed the same assessment protocol and are in The Netherlands. Moreover, the sample of the data recruited in some of the test centers was limited in size. DISCUSSION: The algorithm demonstrated a moderate average predictive performance, and future studies will focus on increasing the stability of the predictive performance across clinical settings.

The relation between depressive and obsessive-compulsive symptoms in obsessive-compulsive disorder: Results from a large, naturalistic follow-up study.

OBJECTIVE: Despite the frequent occurrence of depressive symptoms in obsessive-compulsive disorder (OCD), little is known about the reciprocal influence between depressive and obsessive-compulsive symptoms during the course of the disease. The aim of the present study is to investigate the longitudinal relationship between obsessive-compulsive and depressive symptoms in OCD patients. METHOD: We used the baseline and 1-year follow-up data of the Netherlands Obsessive Compulsive Disorder Association (NOCDA) study. In 276 patients with a lifetime diagnosis of obsessive-compulsive disorder, depressive and obsessive-compulsive symptoms were assessed at baseline and at one-year follow-up with the Beck Depression Inventory (BDI) and the Yale-Brown Obsessive Compulsive Symptom (Y-BOCS) scale. Relations were investigated using a cross-lagged panel design. RESULTS: The association between the severity of depressive symptoms at baseline and obsessive-compulsive symptoms at follow-up was significant (ß=0.244, p<0.001), while the association between the severity of obsessive-compulsive symptoms at baseline and depressive symptoms at follow-up was not (ß=0.097, p=0.060). Replication of the analyses in subgroups with and without current comorbid major depressive disorder (MDD) and subgroups with different sequence of onset (primary versus secondary MDD) revealed the same results. LIMITATIONS: There may be other factors, which affect both depressive and obsessive-compulsive symptoms that were not assessed in the present study. CONCLUSION: The present study demonstrates a relation between depressive symptoms and the course of obsessive-compulsive symptoms in OCD patients, irrespective of a current diagnosis of MDD and the sequence of onset of OCD and MDD.

Validation of the electronic Visual Analogue Scale of Anxiety.

Currently, the use of electronic scales is increasing rapidly, which is not surprising considering its accuracy, the ease of use and the increased compliance. The value of Visual Analogue Scales as a mean to objectify subjective variables has long been recognised. The current study aimed to validate the electronic Visual Analogue Scale of Anxiety (eVAAS). Seventy-one subjects, control subjects (n=46) and Panic Disorder patients (n=25), filled out the paper VAAS and the eVAAS in a randomised order. Panic was provoked using 35% CO(2) inhalation allowing us to include maximal scores in our analyses. The correlation between eVAAS and pVAAS was very strong and highly significant (r=0.98, p<0.001). pVAAS scores were slightly higher than eVAAS scores (p<0.001), but this difference is clinically unimportant. The VAAS established on a tablet PC is a useful and valid measure of anxiety and holds intrinsic benefits for anxiety assessment.

Effect of nicotine on 35% CO2-induced anxiety: A study in healthy volunteers.

Panic disorder and cigarette smoking co-occur at a rate that exceeds what would be expected by chance. Theoretically, cigarette smoking may (a) attenuate panicky symptoms via cognitive factors or pharmacological action, (b) contribute to the development of panic disorder, or (c) share an etiological vulnerability with panic. The present study was aimed at testing whether nicotine has a direct influence on laboratory-elicited panic. In a placebo-controlled, double-blind, randomized, cross-over study, 33 healthy nonsmokers underwent a 35% CO2 challenge after transdermal administration of a nicotine patch on one test day and a placebo patch on another test day. Physiological measures (blood pressure, heart rate) and rating scale scores (Panic Symptom List [PSL], Visual Analog Scale of Anxiety, State-Trait Anxiety Inventory) were assessed. Compared with the placebo condition, nicotine increased diastolic blood pressure (p < .1), heart rate (p < .001), and PSL scores (p < .005) prior to the CO2 challenge but did not affect responding to the CO2 challenge itself. Results are consistent with the notion that nicotine promotes autonomic activation. However, the present study did not provide direct evidence that nicotine elicits panic in healthy volunteers. Replication in a clinical sample is warranted.